[opaque pointer type] Add textual IR support for explicit type parameter to load instruction

Essentially the same as the GEP change in r230786.

A similar migration script can be used to update test cases, though a few more
test case improvements/changes were required this time around: (r229269-r229278)

import fileinput
import sys
import re

pat = re.compile(r"((?:=|:|^)\s*load (?:atomic )?(?:volatile )?(.*?))(| addrspace\(\d+\) *)\*($| *(?:%|@|null|undef|blockaddress|getelementptr|addrspacecast|bitcast|inttoptr|\[\[[a-zA-Z]|\{\{).*$)")

for line in sys.stdin:
  sys.stdout.write(re.sub(pat, r"\1, \2\3*\4", line))

Reviewers: rafael, dexonsmith, grosser

Differential Revision: http://reviews.llvm.org/D7649

llvm-svn: 230794
diff --git a/llvm/test/CodeGen/R600/wait.ll b/llvm/test/CodeGen/R600/wait.ll
index 36b96a2..5cc7577 100644
--- a/llvm/test/CodeGen/R600/wait.ll
+++ b/llvm/test/CodeGen/R600/wait.ll
@@ -9,16 +9,16 @@
 define void @main(<16 x i8> addrspace(2)* inreg %arg, <16 x i8> addrspace(2)* inreg %arg1, <32 x i8> addrspace(2)* inreg %arg2, <16 x i8> addrspace(2)* inreg %arg3, <16 x i8> addrspace(2)* inreg %arg4, i32 inreg %arg5, i32 %arg6, i32 %arg7, i32 %arg8, i32 %arg9, float addrspace(2)* inreg %constptr) #0 {
 main_body:
   %tmp = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %arg3, i32 0
-  %tmp10 = load <16 x i8> addrspace(2)* %tmp, !tbaa !0
+  %tmp10 = load <16 x i8>, <16 x i8> addrspace(2)* %tmp, !tbaa !0
   %tmp11 = call <4 x float> @llvm.SI.vs.load.input(<16 x i8> %tmp10, i32 0, i32 %arg6)
   %tmp12 = extractelement <4 x float> %tmp11, i32 0
   %tmp13 = extractelement <4 x float> %tmp11, i32 1
   call void @llvm.AMDGPU.barrier.global() #1
   %tmp14 = extractelement <4 x float> %tmp11, i32 2
 ;  %tmp15 = extractelement <4 x float> %tmp11, i32 3
-  %tmp15 = load float addrspace(2)* %constptr, align 4 ; Force waiting for expcnt and lgkmcnt
+  %tmp15 = load float, float addrspace(2)* %constptr, align 4 ; Force waiting for expcnt and lgkmcnt
   %tmp16 = getelementptr <16 x i8>, <16 x i8> addrspace(2)* %arg3, i32 1
-  %tmp17 = load <16 x i8> addrspace(2)* %tmp16, !tbaa !0
+  %tmp17 = load <16 x i8>, <16 x i8> addrspace(2)* %tmp16, !tbaa !0
   %tmp18 = call <4 x float> @llvm.SI.vs.load.input(<16 x i8> %tmp17, i32 0, i32 %arg6)
   %tmp19 = extractelement <4 x float> %tmp18, i32 0
   %tmp20 = extractelement <4 x float> %tmp18, i32 1